An investigation of machine learning methods in delta-radiomics feature analysis
Autoři:
Yushi Chang aff001; Kyle Lafata aff002; Wenzheng Sun aff003; Chunhao Wang aff002; Zheng Chang aff002; John P. Kirkpatrick aff002; Fang-Fang Yin aff002
Působiště autorů:
Medical Physics Graduate Program, Duke University, Durham, North Carolina, United States of America
aff001; Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, United States of America
aff002; School of Information Science and Engineering, Shandong University, Qingdao, Shandong, Shandong, People’s Republic of China
aff003; Duke Kunshan University, Kunshan, People’s Republic of China
aff004
Vyšlo v časopise:
PLoS ONE 14(12)
Kategorie:
Research Article
doi:
https://doi.org/10.1371/journal.pone.0226348
Souhrn
Purpose
This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models.
Methods
The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC).
Results
For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889.
Conclusions
The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.
Klíčová slova:
Cancer treatment – Magnetic resonance imaging – Machine learning – Machine learning algorithms – Neural networks – Non-small cell lung cancer – Support vector machines – Stereotactic radiosurgery
Zdroje
1. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2015;278(2):563–77. doi: 10.1148/radiol.2015151169 26579733
2. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441–6. doi: 10.1016/j.ejca.2011.11.036 22257792
3. Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJ. Machine Learning methods for Quantitative Radiomic Biomarkers. Sci Rep. 2015;5:13087. Epub 2015/08/19. doi: 10.1038/srep13087 26278466
4. Parmar C, Grossmann P, Rietveld D, Rietbergen MM, Lambin P, Aerts HJ. Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer Frontiers in oncology. 2015;5:272. Epub 2015/12/24. doi: 10.3389/fonc.2015.00272 26697407
5. Liang C, Huang Y, He L, Chen X, Ma Z, Dong D, et al. The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I-II and stage III-IV colorectal cancer. Oncotarget. 2016;7(21):31401–12. doi: 10.18632/oncotarget.8919 27120787
6. Wu W, Parmar C, Grossmann P, Quackenbush J, Lambin P, Bussink J, et al. Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology Front Oncol. 2016;6:71. doi: 10.3389/fonc.2016.00071 27064691
7. Zhu X, Dong D, Chen Z, Fang M, Zhang L, Song J, et al. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. European radiology. 2018. Epub 2018/02/17. doi: 10.1007/s00330-017-5221-1 29450713.
8. Lafata K, Cai J, Wang C, Hong J, Kelsey CR, Yin FF. Spatial-temporal variability of radiomic features and its effect on the classification of lung cancer histology. Phys Med Biol. 2018;63(22):225003. Epub 2018/10/03. doi: 10.1088/1361-6560/aae56a 30272571.
9. Saha A, Harowicz MR, Wang W, Mazurowski MA. A study of association of Oncotype DX recurrence score with DCE-MRI characteristics using multivariate machine learning models. Journal of cancer research and clinical oncology. 2018. Epub 2018/02/11. doi: 10.1007/s00432-018-2595-7 29427210.
10. Lafata K, Hong J, Geng R, Ackerson B, Liu J-G, Zhou Z, et al. Association of Pre-treatment Radiomic Features with Lung Cancer Recurrence Following Stereotactic Body Radiation Therapy. Physics in Medicine and Biology. 2018.
11. Algohary A, Viswanath S, Shiradkar R, Ghose S, Pahwa S, Moses D, et al. Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: Preliminary findings. Journal of magnetic resonance imaging: JMRI. 2018. Epub 2018/02/23. doi: 10.1002/jmri.25983 29469937.
12. Tu SJ, Wang CW, Pan KT, Wu YC, Wu CT. Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening. Phys Med Biol. 2018. Epub 2018/02/16. doi: 10.1088/1361-6560/aaafab 29446758.
13. Sollini M, Cozzi L, Chiti A, Kirienko M. Texture analysis and machine learning to characterize suspected thyroid nodules and differentiated thyroid cancer: Where do we stand? European journal of radiology. 2018;99:1–8. Epub 2018/01/25. doi: 10.1016/j.ejrad.2017.12.004 29362138.
14. Garapati SS, Hadjiiski L, Cha KH, Chan HP, Caoili EM, Cohan RH, et al. Urinary bladder cancer staging in CT urography using machine learning. Medical Physics. 2017;44(11):5814–23. doi: 10.1002/mp.12510 28786480
15. Leger S, Zwanenburg A, Pilz K, Lohaus F, Linge A, Zophel K, et al. A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling. Sci Rep. 2017;7(1):13206. doi: 10.1038/s41598-017-13448-3 29038455
16. Mattonen SA, Palma DA, Johnson C, Louie AV, Landis M, Rodrigues G, et al. Detection of Local Cancer Recurrence After Stereotactic Ablative Radiation Therapy for Lung Cancer: Physician Performance Versus Radiomic Assessment. International Journal of Radiation Oncology • Biology • Physics. 94(5):1121–8. doi: 10.1016/j.ijrobp.2015.12.369 26907916
17. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature communications. 2014;5:4006. doi: 10.1038/ncomms5006 24892406
18. Fave X, Zhang L, Yang J, Mackin D, Balter P, Gomez D, et al. Delta-radiomics features for the prediction of patient outcomes in non–small cell lung cancer. Scientific Reports. 2017;7(1):588. doi: 10.1038/s41598-017-00665-z 28373718
19. Rao SX, Lambregts DM, Schnerr RS, Beckers RC, Maas M, Albarello F, et al. CT texture analysis in colorectal liver metastases: A better way than size and volume measurements to assess response to chemotherapy? United European Gastroenterol J. 2016;4(2):257–63. doi: 10.1177/2050640615601603 27087955
20. Cunliffe A, Armato SG 3rd, Castillo R, Pham N, Guerrero T, Al-Hallaq HA. Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. Int J Radiat Oncol Biol Phys. 2015;91(5):1048–56. doi: 10.1016/j.ijrobp.2014.11.030 25670540
21. Carvalho S, Leijenaar RTH, Troost EGC, van Elmpt W, Muratet JP, Denis F, et al. Early variation of FDG-PET radiomics features in NSCLC is related to overall survival—the “delta radiomics” concept. Radiotherapy and Oncology. 118:S20–S1. doi: 10.1016/S0167-8140(16)30042-1
22. Grossmann P, Narayan V, Huang R, Aerts H. TU-D-207B-07: Radiomic Response Assessment for Recurrent Glioblastoma Treated with Bevacizumab in the BRAIN Trial Medical physics. 2016;43(6Part34):3751–2.
23. Zhang Z, Yang J, Ho A, Jiang W, Logan J, Wang X, et al. A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images. European radiology. 2017. doi: 10.1007/s00330-017-5154-8 29178031
24. van Timmeren JE, Leijenaar RTH, van Elmpt W, Reymen B, Lambin P. Feature selection methodology for longitudinal cone-beam CT radiomics. Acta Oncol. 2017;56(11):1537–43. doi: 10.1080/0284186X.2017.1350285 28826307.
25. Zhang B, He X, Ouyang F, Gu D, Dong Y, Zhang L, et al. Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma. Cancer letters. 2017;403:21–7. doi: 10.1016/j.canlet.2017.06.004 28610955
26. Wang C, Sun W, Kirkpatrick J, Chang Z, Yin F-F. Assessment of concurrent stereotactic radiosurgery and bevacizumab treatment of recurrent malignant gliomas using multi-modality MRI imaging and radiomics analysis. Journal of Radiosurgery and SBRT. 2018;5(3):171–81. 29988289
27. Haralick RM, Shanmugam K. Textural features for image classification. IEEE Transactions on systems, man, and cybernetics. 1973;(6):610–21.
28. Galloway MM. Texture analysis using grey level run lengths. NASA STI/Recon Technical Report N. 1974;75.
29. Thibault G, Angulo J, Meyer F. Advanced statistical matrices for texture characterization: application to cell classification. IEEE Trans Biomed Eng. 2014;61(3):630–7. doi: 10.1109/TBME.2013.2284600 24108747.
30. Amadasun M, King R. Textural features corresponding to textural properties. IEEE Transactions on systems, man, and Cybernetics. 1989;19(5):1264–74.
31. Zwanenburg A, Leger S, Vallières M, Löck S. Image biomarker standardisation initiative-feature definitions. arXiv preprint arXiv:161207003. 2016.
32. Cox DR. The regression analysis of binary sequences. Journal of the Royal Statistical Society Series B (Methodological). 1958:215–42.
33. Breiman L. Random forests. Machine learning. 2001;45(1):5–32.
34. Hecht-Nielsen R. Theory of the backpropagation neural network. Neural networks for perception: Elsevier; 1992. p. 65–93.
35. Rish I, editor An empirical study of the naive Bayes classifier. IJCAI 2001 workshop on empirical methods in artificial intelligence; 2001: IBM.
36. Manning CD, Raghavan P, Schütze H. Text classification and naive bayes. Introduction to information retrieval. 2008;1:6.
37. Tohka J, Moradi E, Huttunen H, Alzheimer’s Disease Neuroimaging I. Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia. Neuroinformatics. 2016;14(3):279–96. doi: 10.1007/s12021-015-9292-3 26803769
38. Hua J, Xiong Z, Lowey J, Suh E, Dougherty ER. Optimal number of features as a function of sample size for various classification rules. Bioinformatics. 2005;21(8):1509–15. doi: 10.1093/bioinformatics/bti171 15572470
39. Huang H-C, Qin L-X. Empirical evaluation of data normalization methods for molecular classification. PeerJ. 2018;6:e4584. doi: 10.7717/peerj.4584 29666754
40. Simon RM, Subramanian J, Li M-C, Menezes S. Using cross-validation to evaluate predictive accuracy of survival risk classifiers based on high-dimensional data. Briefings in Bioinformatics. 2011;12(3):203–14. doi: 10.1093/bib/bbr001 21324971
41. Metz CE, editor Basic principles of ROC analysis. Seminars in nuclear medicine; 1978: Elsevier.
42. Fawcett T. An introduction to ROC analysis. Pattern recognition letters. 2006;27(8):861–74.
Článek vyšel v časopise
PLOS One
2019 Číslo 12
- Tisícileté topoly, mokří psi, stárnoucí kočky a ospalé octomilky – „jednohubky“ z výzkumu 2024/41
- Jaké jsou aktuální trendy v léčbě karcinomu slinivky?
- Může hubnutí souviset s vyšším rizikem nádorových onemocnění?
- Menstruační krev má značný diagnostický potenciál, mimo jiné u diabetu
- Metamizol jako analgetikum první volby: kdy, pro koho, jak a proč?
Nejčtenější v tomto čísle
- Methylsulfonylmethane increases osteogenesis and regulates the mineralization of the matrix by transglutaminase 2 in SHED cells
- Oregano powder reduces Streptococcus and increases SCFA concentration in a mixed bacterial culture assay
- The characteristic of patulous eustachian tube patients diagnosed by the JOS diagnostic criteria
- Parametric CAD modeling for open source scientific hardware: Comparing OpenSCAD and FreeCAD Python scripts
Zvyšte si kvalifikaci online z pohodlí domova
Všechny kurzy